INDEX

Explanations

instances of the word "scoop" and its variations

oai_token-act-pair · gpt-3.5-turbo

instances of the word "scoop" and related variations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

lihood

-0.75

idency

-0.72

 livest

-0.71

audi

-0.66

usable

-0.64

repeat

-0.64

senal

-0.63

uctor

-0.62

 pathways

-0.62

 diligence

-0.62

POSITIVE LOGITS

 scoop

1.12

iest

0.95

iness

0.92

sheet

0.88

oops

0.86

fall

0.85

hest

0.84

sters

0.84

sheets

0.80

ing

0.77

Activations Density 0.019%

instances of the word "scoop" and its variations

instances of the word "scoop" and related variations

No Comments

No Known Activations